watchface_clock_catalog

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must carry the full behavioral burden, and it does disclose unusually valuable context: the data's provenance (generated from both simulator clocksys directories), the meaning of the default set (Device/GetClockDefaultList with IsDefault=1), and that TimesFrame data is independent. It stops short of stating that the call is read-only and never mentions rate limits or response shape, but the provenance and prerequisite chain are exactly the kind of info annotations could not supply.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The returned-field inventory is front-loaded in sentence one, with conditional model caveats following, so an agent can stop reading early if it's on TimesFrame. It is somewhat dense with internal jargon (clocksys, Device/GetClockDefaultList) and the AstroToo/TimesFrame threading could be tighter, but no sentence is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter tool with a nested target object, no output schema, and no annotations, the description supplies the two things an agent most needs: what rows contain and model-specific caveats. With full schema coverage on filters and defaults, the remaining gap (no explicit statement that the operation is read-only, no pagination behavior beyond the limit param) is minor.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description still earns a point by explaining what 'default' actually means for defaultOnly (the Device/GetClockDefaultList IsDefault=1 set) and by reinforcing that model is for offline authoring only. Filters like disps/fonts/tagsAny are covered only by their schema text, which is adequate given full coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence names a specific verb (query) and enumerates exactly what the tool returns: ClockId, Chinese/English names, font ids, disp ids, item ids, and optional source configuration. That is far more informative than a tautology, though it never names the sibling catalogs (watchface_font_catalog, watchface_disp_catalog) that overlap with the font/disp fields, so differentiation is left to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There are real prerequisites ('For AstroToo, first query hardware/capabilities; use the 480x480 AstroToo resources') and a scope restriction ('Legacy 800x1280 examples and typography apply only to TimesFrame'), which is more than most tools offer. However, there is no guidance on when to use this catalog instead of watchface_font_catalog or watchface_disp_catalog, even though both presumably cover a subset of these fields.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.